© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 3820
    Prev
    Next
    INDEX
    Explanations

    prefixes, titles, and articles

    oai_token-act-pair · gemini-2.0-flash

    co

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     onOptions
    -0.59
     Bunga
    -0.57
     elastici
    -0.57
    __':
    -0.55
     zirc
    -0.52
     scro
    -0.50
     ExecuteAsync
    -0.49
     EXTRACT
    -0.49
    Filmografia
    -0.48
    didSet
    -0.48
    POSITIVE LOGITS
    HEC
    0.54
    SharedCtor
    0.54
    MCA
    0.52
    formis
    0.51
    erra
    0.50
    atella
    0.50
    COA
    0.50
    liggende
    0.49
    settling
    0.48
    ordonnées
    0.48
    Activations Density 9.105%

    No Known Activations